Get started

Procedure

If you are new to the Alibaba Cloud Vision AI Platform, follow these steps to get started.

1. Step 1: Become a developer

2. Step 2: Test a capability

3. Step 3: Activate a capability

4. Step 4: Create an AccessKey

5. Step 5: Start development

Step 1: Become a developer

1. Register an Alibaba Cloud account.

   1. Go to the Alibaba Cloud official website and click Register Now in the upper-right corner.

   2. On the Register page, follow the on-screen instructions to complete the registration.

      Your Alibaba Cloud account is the primary account for resource consumption and has full permissions for all of its resources.

      Important

      To ensure the security of your account, do not share your credentials and update your password regularly.

2. Complete real-name verification for your Alibaba Cloud account.

   You must complete real-name verification for your Alibaba Cloud account to purchase and use Alibaba Cloud products.

   1. Go to the Account Management page.

   2. In the left-side navigation pane, follow the instructions to complete real-name verification.

      If you are an enterprise user, we recommend that you complete enterprise verification to access additional features. For more information, see Real-name Verification.

      Important

      Only users who have completed enterprise verification can activate AI capabilities in the Face & Body category.

3. Grant RAM permissions.

   If you need to use a RAM user to activate services on the Alibaba Cloud Vision AI Platform, ensure the RAM user has the necessary permissions to access Alibaba Cloud resources. For more information about how to grant permissions, see Control access with RAM policies.

   Important

   Make sure your RAM user is granted the AliyunVIAPIFullAccess permission. Otherwise, the RAM user cannot activate or purchase services on the Alibaba Cloud Vision AI Platform.

Step 2: Test a capability

1. Log in to the Alibaba Cloud Vision AI Platform with your Alibaba Cloud account.

2. In the top navigation bar, click Solutions. Select Text Recognition > id card recognition to go to the experience center for this capability.

   The left-side navigation pane lists capability categories. The main area displays capabilities grouped by subcategory. The id card recognition capability is in the Personal card/certificate recognition group.

3. Select the side of the ID card to recognize based on the photo.

4. Upload a photo of an ID card for recognition.

   • Method 1: Click Upload Image to upload the ID card photo and start the call.

   • Method 2: Enter the image URL in the input box below and click the icon to its right to start the call.

   At the top of the Product experience page, you can switch between the National emblem side and Portrait side tabs. The image to be recognized appears on the left. The Call result area in the middle shows the recognized fields, such as issuing authority and expiration date. The Sample image panel is on the right. At the bottom, you can click Download result to export the results.

5. View the call results at the bottom of the page.

   • Result code: Shows the full API response from the call.

   • Sample code: Shows SDK code samples for various programming languages, such as Java, Python, and Node.js.

   • Technical documentation: Shows the technical documentation for the API.

   This panel contains the Result code, Input parameters, and Request address tabs. The Result code tab displays the complete API response data in JSON format, including the recognized field values and request metadata.

Step 3: Activate a capability

1. At the top of the capability page, click Activate Now to go to the purchase page. This page shows details about the id card recognition capability and provides links to Buy now, Technical documentation, and Product price.

2. Select a region and the capabilities that you want to purchase, select the service agreements, and click Activate now at the bottom. You can select the China (Shanghai) or China (Shenzhen) region. The page lists all paid capabilities in the text recognition category. The service agreements include the Paid Capability Universal Agreement and the Public Preview Trial Agreement.

   Note

   • Activating an AI capability in a category allows you to call all capabilities within that category. Activating a capability does not incur charges.

   • Capabilities in public preview are free to use.

   • For information about the billing and purchasing methods for paid capabilities, see Billable Items.

   After activation, you can choose to go to the console or view the category documentation.

   A success message is displayed on the page. Service deployment takes 1 to 5 minutes.

Step 4: Create an AccessKey

You must create an AccessKey before you can use an Alibaba Cloud SDK or call APIs of the Alibaba Cloud Vision AI Platform. You can create and manage your AccessKey on the AccessKey Management page in your account portal. For more information, see Create an AccessKey.

Step 5: Start development

1. Download and install the SDK package.

   The SDK supports six popular programming languages: Java, Python, Go, Node.js, PHP, and C#. You can choose the appropriate SDK for your language to integrate visual AI capabilities.

2. Start calling the API.

   Refer to the id card recognition API documentation to begin your development.

   For detailed descriptions and usage instructions for other capability categories, see: Generation, Face & Body, text recognition, Product Understanding, content moderation, image recognition, image generation, image segmentation, visual search, Image Analysis and Processing, object detection, video understanding, video generation, and video segmentation.

Reference implementation

For a complete Java implementation of an id card recognition system, see the Development Code Sample. You can use this sample to set up a Spring Boot project and call the services.

Contact us

If you have any questions, join our DingTalk support group (ID: 23109592). We provide 24/7 expert support.